Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4890 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.6817. Min Act: -0.1700
Data Index: 31403 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.4005. Min Act: -0.1700
Data Index: 4134325 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.3380. Min Act: -0.1700
Data Index: 7495008 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.3067. Min Act: -0.1700
Data Index: 7694076 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.2442. Min Act: -0.1700
Data Index: 7008780 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.2130. Min Act: -0.1700
Data Index: 8684183 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.2442. Min Act: -0.1700
Data Index: 7960299 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.2442. Min Act: -0.1700
Data Index: 3281763 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.2442. Min Act: -0.1700
Data Index: 2026938 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.2442. Min Act: -0.1700
Data Index: 1217231 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.2130. Min Act: -0.1700
Data Index: 7975871 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.1817. Min Act: -0.1700
Data Index: 7519991 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.1505. Min Act: -0.1700
Data Index: 2604688 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.1505. Min Act: -0.1700
Data Index: 5864024 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.1505. Min Act: -0.1700
Data Index: 2606979 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.1192. Min Act: -0.1700
Data Index: 6070347 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.1192. Min Act: -0.1700
Data Index: 4622 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.0880. Min Act: -0.1700
Data Index: 1343147 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.0567. Min Act: -0.1700
Data Index: 7948764 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6817. Min Range: -7.6817
Max Act: 7.0880. Min Act: -0.1700
Data Index: 7475590 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19